Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...
Tested on 10 benchmarks · BenchGecko score 22.6. Top scores: HELM · WildBench (78.8%), HELM · IFEval (75.0%), HELM · MMLU-Pro (61.0%).
Gemma 3 27B scores 22.6 (100% as good) at $0.08/1M input · 77% cheaper
Stanford HELM WildBench evaluation. Tests reasoning on challenging real-world tasks.
Competition-level math from AMC, AIME, and olympiad problems. Level 5 is the hardest tier, requiring creative problem-solving.
Stanford HELM evaluation of mathematical reasoning across diverse problem types.
Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.
Stanford HELM evaluation of MMLU-Pro. Tests broad knowledge with increased difficulty.
Graduate-level science questions written by PhD experts. Diamond subset contains questions where experts disagree, testing deep understanding.
- Typemultimodal
- Context128K tokens (~64 books)
- ReleasedMar 2025
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.001
Frequently Asked Questions
Key facts · as of 2026-11-11
- Mistral Small 3.1 24B by Mistral AI. BenchGecko score 22.6, rank 285 of 326 scored models (normalized average of public benchmark scores).
- List price $0.35 input · $0.56 output per 1M tokens (as of 2026-11-11).
- Sold by 1 provider (as of 2026-11-11): Cloudflare $0.35 in / $0.56 out.
How to cite · data as of 2026-11-11
Mistral Small 3.1 24B · benchmarks, pricing and providers. BenchGecko, data as of 2026-11-11. https://benchgecko.ai/model/mistral-small-3-1-24b-instruct
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP